Du 14 au 17 octobre, Olivier Simonin a co-présidé avec François Charpillet (Inria Nancy) les JNRR 2019 Journées Nationales de la Recherche en Robotique, qui se sont tenues à Vittel et parrainées par le GDR Robotique. Le 13 octobre était également organisée la Journée des Jeunes Chercheurs en Robotique JJCR, et les 17/18 un tutoriel Apprentissage & Robotique était organisé par Christian Wolf et David Filliat.

L’événement, qui a lieu tous les 2 ans, a eu un fort succès en accueillant 200 participants, qui ont pu suivre 27 exposés scientifiques sur 3 jours.

Site des JNRR 2019 (accès au programme) : https://jnrr2019.loria.fr/

Title: Pedestrian Behavior Modeling and Simulation from Real Time Data Information

Date and Place: 22 / 11 / 2019 09:00 in TD-D

Speaker: John Manuel Delgado and Michael Puentes (TInteresaLab de Unidades Tecnológicas de Santander – UTS, Colombia)

Host: Oscar Carrillo

Abstract:
Accidents of pedestrians sometimes take lives, in Bucaramanga since 2012 pedestrian died by accidents are 179, and 2873 hurt, In a city like Bucaramanga-Colombia, this means each day at least one pedestrian is involved in an accident. Therefore is necessary to know the causes of accidents in the way to decrease the accidents. One of many reasons to know the causes is with system dynamics, simulating the events of the Pedestrian behavior when accidents occur in risen cities. The implementation simulation joint with technology and research looking for saving lives, reducing the accidental rate, and to implementing or suggesting new policies from the government. This project is looking for the implementation of technology in video records and Deep Learning analysis for the service of the citizens, where a simulation model will be revealing the main variables which intervene in the pedestrian’s behavior. As initials results, shows the methodology here implemented, can reach data which was insufficient before thanks to the cameras and software of objects detection, those are the data input for the simulation model, which after to implement a change in a particular spot of Bucaramanga is possible to decrease the accident rate in 80% where pedestrians could be involved.

Title: Design of Optimal Multiplierless FIR Filters

Date and Place: 13 / 11 / 2019 10:30 in TD-C

Speaker: Martin Kumm (University of Applied Sciences Fulda, Germany)

Host: Florent de Dinechin

Abstract:
In this talk we present a novel method for the simultaneous design of digital filters adhering to a given frequency specification and its dedicated (hardware) implementation. Our methods are based on an integer linear programming (ILP) problem and aim to minimize the number of adders used to implement a digital filter. In the first part, an overview is given about the structure of finite impulse response (FIR) filters which typically contain many costly multiplications. As these are usually multiplications by a constant, they can be reduced to additions, subtractions and bit-shifts, leading to a multiplierless realization. A brief overview of state-of-the-art methods for optimizing constant multiplications is presented. In the second part, novel extensions are presented that also consider the frequency specification of the digital filter in the optimization. Compared to previous multiplierless FIR approaches, the methods introduced here ensure adder count optimality. We show the effectiveness by solving established design problems: our results either prove existing heuristics to be optimal or improve their adder count.

Biography:
Martin Kumm is full professor in the faculty of Applied Computer Science at the University of Applied Sciences Fulda in Germany. His research interests are arithmetic circuits and their optimization in the context of reconfigurable systems (FPGAs). http://www.martin-kumm.de/

Title: The Bouncer Problem: Challenges to Remote Explainability

Date and Place: 09 / 10 / 2019 3PM in 432 (Antenne Inria)

Host: Privatics

Abstract:
The concept of explainability is envisioned to satisfy society’s demands for transparency on machine learning decisions. The concept is simple: like humans, algorithms should explain the rationale behind their decisions so that their fairness can be assessed. While this approach is promising in a local context (e.g. to explain a model during debugging at training time), we argue that this reasoning cannot simply be transposed in a remote context, where a trained model by a service provider is only accessible through its API. This is problematic as it constitutes precisely the target use-case requiring transparency from a societal perspective. Through an analogy with a club bouncer (which may provide untruthful explanations upon customer reject), we show that providing explanations cannot prevent a remote service from lying about the true reasons leading to its decisions.

More precisely, we prove the impossibility of remote explainability for single explanations, by constructing an attack on explanations that hides discriminatory features to the querying user. We provide an example implementation of this attack. We then show that the probability that an observer spots the attack, using several explanations for attempting to find incoherences, is low in practical settings. This undermines the very concept of remote explainability in general.

Biography:
Erwan is on an “advanced research position” at Inria, in the WIDE team, since Nov. 2018. He was previously senior research scientist at Technicolor R&I (2009-2018). Gilles is a “chargé de recherches” at CNRS since 2011.

Title: On False Data Injection Attacks Against Power Grids and Countermeasures

Date and Place: 19 / 09 / 2019 2PM in TD-C

Host: Samir M. Perlaza

Abstract:
The power grid state estimation (SE) has been shown to be vulnerable to false data injection (FDI) attacks, which can lead to severe consequences, e.g., transmission line trips, unsafe frequency excursions and/or economic losses. In this talk, we will examine the security of power gird SE from both the attacker and the defender’s perspective. For the former, we examine data-driven FDI attacks, i.e., constructing FDI attacks that can bypass the grid’s bad-data detector (BDD) by accessing its measurement data over a period of time. We characterize important tradeoffs for the attacker in this context between the attack’s spatial and temporal efficiency. The results provide us with an understanding for designing defense mechanism to thwart such attacks. For defense, we propose a hardened-attack detector based on moving-target defense (MTD) that actively perturbs transmission line reactances to invalidate the attacker’s knowledge. We present novel formal design criteria to select MTD reactance perturbations that are truly effective. Moreover, based on a key optimal power flow formulation, we find that the effective MTD may incur a non-trivial operational cost. Accordingly, we characterize important tradeoffs between the MTD’s detection capability and its associated required cost. Extensive simulations, using the MATPOWER simulator and benchmark IEEE bus systems, verify and illustrate the proposed design approach.

Biography:
Subhash Lakshminarayana is an assistant professor in the University of Warwick’s School of Engineering since September 2018. Prior to joining Warwick, he worked as a research scientist at the Advanced Digital Sciences Center (ADSC) in Singapore between 2015-2018. Before that, he held joint post-doctoral researcher appointment at Princeton University and the Singapore University of Technology and Design (SUTD) between 2013-2015. He received his PhD in the field of Wireless Communications at the Department of Telecommunications at Ecole Superieure d’Electricite (Supelec) Paris, France, M.S. degree from The Ohio State University, USA and B.S. from Bangalore University in India. His research interests include cyber-physical system security (power grids and urban transportation) and wireless communications. His works have been selected among the Best Conference Papers at the IEEE Power Energy Society General Meeting (PESGM) 2015 conference, and the Best 50 Papers at the IEEE Globecom 2014 conference.

Title: Time-Dependent and Stochastic Vehicle Routing Problems

Date and Place: 26 / 09 / 2019 14:00 in TD-C

Host: Florent de Dinechin

Abstract:
Smart cities are equipped with sensors which monitor traffic speed. The exploitation of these data to optimise urban deliveries has given rise to new challenging problems, and I’ll focus on two of them: – Time-Dependent Vehicle Routing Problems, which take into account variations of travel speeds during the day; – Stochastic Vehicle Routing Problems, where uncertain data are represented by random variables.

Biography:
Christine Solnon is Professor in the Computer Science Department of INSA Lyon, and member of the LIRIS lab.